feat: llm.chat.v1 multi-turn supplier type + free Kimi K2.6 chat demo
Some checks failed
CI / typecheck + vitest (Node 20) (push) Has been cancelled

Adds a conversational supplier capability and a free demo, both streaming.

New paid `llm.chat.v1` type: one escrow per conversation (flat fee). "Start
chat" posts the escrow with a session-init placeholder prompt_hash and the
supplier Claims (reserving its single slot); turns then stream off-chain via
SSE with zero chain interaction; "End chat" has the supplier Submit a receipt
over the full transcript and the buyer Accept — the moment the user is charged.
The on-chain validator is content-agnostic (pins but never verifies the
hashes), so this reuses the existing contract unchanged. A supplier-side idle
watchdog auto-ends abandoned sessions before deliver_by.

Free Kimi K2.6 chat demo: a synthetic "demo:kimi-chat" tile that uses the same
chat UI but proxies straight to OpenRouter (no escrow, no payment), mirroring
the existing Piper demo.

Shared:
- postChatEscrow.ts + chatSessionPromptHash() (session-init prompt_hash helper
  shared by the buyer builder and the supplier start gate).

Supplier:
- CAPABILITY_KIND="chat-session" (+ CHAT_IDLE_TIMEOUT_MS); callOpenAiStream()
  streaming client; ChatSessionStore + endChatSession(); /v1/chat/{start,
  message,end} handlers with idle + hard-cap watchdog timers.

Buyer:
- Marketplace.startChat()/endChat() with relaxed (session-init) receipt
  verification + crypto verifyReceipt; /v1/chat/{start,message,end} routes
  (SSE passthrough) and a free /v1/chat-demo/message OpenRouter proxy;
  OPENROUTER_API_KEY/OPENROUTER_BASE_URL config; ChatForm.tsx + Dashboard
  KIMI_DEMO_SUPPLIER tile and llm.chat.v1 dispatch.

Deploy:
- docker-compose.supplier-kimi-chat.yml + supplier/.env.kimi-chat.example.

Typecheck passes across all workspaces; full vitest suite green except 15
pre-existing time-bomb/RED failures (tx-claim/accept/post-advert live-CBOR
fixtures with hardcoded past deadlines + the M0-C golden-datum test), confirmed
identical on a clean tree.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
david
2026-06-08 16:18:54 +02:00
parent e01a03b7f2
commit 9acad5b2b8
17 changed files with 1997 additions and 13 deletions

View File

@@ -0,0 +1,86 @@
# deploy/mainnet/docker-compose.supplier-kimi-chat.yml — Supplier — MAINNET
# (OpenRouter / Kimi K2.6 — MULTI-TURN CHAT capability `llm.chat.v1`)
#
# The chat-session sibling of docker-compose.supplier-kimi.yml. Same image,
# same OpenRouter backend (moonshotai/kimi-k2.6), but CAPABILITY_KIND=chat-session
# so it mounts /v1/chat/{start,message,end} (escrow bookends, off-chain
# streaming turns) instead of the one-off /v1/chat/completions route.
#
# A SEPARATE process/advert from the one-off Kimi supplier on purpose: the
# chat session holds the supplier's single-slot lock for the whole conversation
# (minutes), which would starve one-off traffic if co-hosted.
#
# Coexists with:
# - marketplace-mainnet-supplier-kimi (one-off llm.text.generate.v1, mp-suppliers-kimi.vector.apexfusion.org)
#
# Pre-flight:
# 1. DNS A-record: mp-suppliers-kimi-chat.vector.apexfusion.org → host IP
# 2. supplier/.env.kimi-chat written on host (chmod 600) with at minimum:
# SUPPLIER_PRIV_KEY_HEX, OPENAI_API_KEY, OGMIOS_URL, NETWORK_ID=1,
# VECTOR_ZERO_TIME_MS, ESCROW_REF_UTXO, ADVERT_REF_UTXO, ADVERT_REF,
# LIVE_CHAIN=1
# The advert must be posted with --capability-id llm.chat.v1 and a large
# --max-processing-ms (~1800000) so Claim+Submit both land before deliver_by.
# 3. Networks already exist (created by the canonical supplier compose):
# docker network create marketplace-mainnet-net # one-shot
# # traefik-net is created by the Traefik project
name: marketplace-mainnet-supplier-kimi-chat
services:
supplier:
build:
context: ../..
dockerfile: supplier/Dockerfile
container_name: marketplace-mainnet-supplier-kimi-chat
restart: unless-stopped
env_file:
# Self-contained env for the Kimi-chat variant — separate from
# ../../supplier/.env.kimi (the one-off Kimi supplier). Holds this
# supplier's distinct SUPPLIER_PRIV_KEY_HEX, ADVERT_REF (an llm.chat.v1
# advert), OPENAI_API_KEY, and the shared mainnet plumbing.
- path: ../../supplier/.env.kimi-chat
required: false
environment:
# Multi-turn chat session capability (mounts /v1/chat/{start,message,end}).
CAPABILITY_KIND: chat-session
LLM_BACKEND: openai
# No /v1 suffix — supplier/src/openai.ts appends /v1/chat/completions.
OPENAI_BASE_URL: https://openrouter.ai/api
# Kimi K2.6 generations can be slow; mirror the one-off Kimi compose.
OPENAI_TIMEOUT_MS: "300000"
# Auto-end an idle session after 5 min (supplier Submits the transcript).
CHAT_IDLE_TIMEOUT_MS: "300000"
PORT: "8080"
# Enable LiveOgmiosProvider so Claim/Submit actually broadcast.
LIVE_CHAIN: "1"
# NETWORK_ID and OGMIOS_URL intentionally not pinned here — they MUST
# come from the operator-provided supplier/.env.kimi-chat on a mainnet host.
healthcheck:
test: ["CMD-SHELL", "wget -qO- http://localhost:8080/healthz >/dev/null || exit 1"]
interval: 20s
timeout: 5s
retries: 3
start_period: 15s
networks:
- marketplace-mainnet-net
- traefik-net
labels:
- "traefik.enable=true"
- "traefik.docker.network=traefik-net"
- "traefik.http.routers.mp-suppliers-kimi-chat-mainnet.entrypoints=web"
- "traefik.http.routers.mp-suppliers-kimi-chat-mainnet.rule=Host(`mp-suppliers-kimi-chat.vector.apexfusion.org`)"
- "traefik.http.services.mp-suppliers-kimi-chat-mainnet.loadbalancer.server.port=8080"
logging:
driver: json-file
options:
max-size: "10m"
max-file: "3"
networks:
marketplace-mainnet-net:
external: true
name: marketplace-mainnet-net
traefik-net:
external: true
name: traefik-net